1
|
Liang X, Guo M, Jiang L, Fu Y, Zhang P, Chen Y. Predicting miRNA-Disease Associations by Combining Graph and Hypergraph Convolutional Network. Interdiscip Sci 2024; 16:289-303. [PMID: 38286905 DOI: 10.1007/s12539-023-00599-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Revised: 12/15/2023] [Accepted: 12/17/2023] [Indexed: 01/31/2024]
Abstract
miRNAs are important regulators for many crucial biological processes. Many recent studies have shown that miRNAs are closely related to various human diseases and can be potential biomarkers or therapeutic targets for some diseases, such as cancers. Therefore, accurately predicting miRNA-disease associations is of great importance for understanding and curing diseases. However, how to efficiently utilize the characteristics of miRNAs and diseases and the information on known miRNA-disease associations for prediction is still not fully explored. In this study, we propose a novel computational method for predicting miRNA-disease associations. The proposed method combines the graph convolutional network and the hypergraph convolutional network. The graph convolutional network is utilized to extract the information from miRNA-similarity data as well as disease-similarity data. Based on the representations of miRNAs and diseases learned by the graph convolutional network, we further use the hypergraph convolutional network to capture the complex high-order interactions in the known miRNA-disease associations. We conduct comprehensive experiments with different datasets and predictive tasks. The results show that the proposed method consistently outperforms several other state-of-the-art methods. We also discuss the influence of hyper-parameters and model structures on the performance of our method. Some case studies also demonstrate that the predictive results of the method can be verified by independent experiments.
Collapse
Affiliation(s)
- Xujun Liang
- Department of Oncology, NHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China.
- National Clinical Research Center for Gerontology, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China.
| | - Ming Guo
- Department of Oncology, NHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China
- National Clinical Research Center for Gerontology, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China
| | - Longying Jiang
- Department of Oncology, NHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China
- Department of Pathology, Xiangya Hospital, Central South University, Xiangya Road, Changsha, China, 410008
| | - Ying Fu
- Department of Oncology, NHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China
- National Clinical Research Center for Gerontology, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China
| | - Pengfei Zhang
- Department of Oncology, NHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China
- National Clinical Research Center for Gerontology, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China
| | - Yongheng Chen
- Department of Oncology, NHC Key Laboratory of Cancer Proteomics, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China.
- National Clinical Research Center for Gerontology, Xiangya Hospital, Central South University, Xiangya Road, Changsha, 410008, China.
| |
Collapse
|
2
|
Das SS, Saha P, Chakravorty N. miRwayDB: a database for experimentally validated microRNA-pathway associations in pathophysiological conditions. DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION 2018; 2018:4915493. [PMID: 29688364 PMCID: PMC5829561 DOI: 10.1093/database/bay023] [Citation(s) in RCA: 29] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/01/2017] [Accepted: 02/07/2018] [Indexed: 01/31/2023]
Abstract
MicroRNAs (miRNAs) are well-known as key regulators of diverse biological pathways. A series of experimental evidences have shown that abnormal miRNA expression profiles are responsible for various pathophysiological conditions by modulating genes in disease associated pathways. In spite of the rapid increase in research data confirming such associations, scientists still do not have access to a consolidated database offering these miRNA-pathway association details for critical diseases. We have developed miRwayDB, a database providing comprehensive information of experimentally validated miRNA-pathway associations in various pathophysiological conditions utilizing data collected from published literature. To the best of our knowledge, it is the first database that provides information about experimentally validated miRNA mediated pathway dysregulation as seen specifically in critical human diseases and hence indicative of a cause-and-effect relationship in most cases. The current version of miRwayDB collects an exhaustive list of miRNA-pathway association entries for 76 critical disease conditions by reviewing 663 published articles. Each database entry contains complete information on the name of the pathophysiological condition, associated miRNA(s), experimental sample type(s), regulation pattern (up/down) of miRNA, pathway association(s), targeted member of dysregulated pathway(s) and a brief description. In addition, miRwayDB provides miRNA, gene and pathway score to evaluate the role of a miRNA regulated pathways in various pathophysiological conditions. The database can also be used for other biomedical approaches such as validation of computational analysis, integrated analysis and prediction of computational model. It also offers a submission page to submit novel data from recently published studies. We believe that miRwayDB will be a useful tool for miRNA research community. Database URL: http://www.mirway.iitkgp.ac.in
Collapse
Affiliation(s)
- Sankha Subhra Das
- School of Medical Science and Technology, Indian Institute of Technology, Kharagpur, West Bengal, 721302, India
| | - Pritam Saha
- Cryogenic Engineering Centre, Indian Institute of Technology, Kharagpur, West Bengal, 721302, India
| | - Nishant Chakravorty
- School of Medical Science and Technology, Indian Institute of Technology, Kharagpur, West Bengal, 721302, India
| |
Collapse
|
3
|
Wei G, Sun L, Qin S, Li R, Chen L, Jin P, Ma F. Dme-Hsa Disease Database (DHDD): Conserved Human Disease-Related miRNA and Their Targeting Genes in Drosophila melanogaster. Int J Mol Sci 2018; 19:ijms19092642. [PMID: 30200613 PMCID: PMC6163619 DOI: 10.3390/ijms19092642] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2018] [Revised: 08/29/2018] [Accepted: 08/31/2018] [Indexed: 12/24/2022] Open
Abstract
Abnormal expressions of microRNA (miRNA) can result in human diseases such as cancer and neurodegenerative diseases. MiRNA mainly exert their biological functions via repressing the expression of their target genes. Drosophila melanogaster (D. melanogaster) is an ideal model for studying the molecular mechanisms behind biological phenotypes, including human diseases. In this study, we collected human and D. melanogaster miRNA as well as known human disease-related genes. In total, we identified 136 human disease-related miRNA that are orthologous to 83 D. melanogaster miRNA by mapping "seed sequence", and 677 human disease-related genes that are orthologous to 734 D. melanogaster genes using the DRSC Integrative Ortholog Prediction Tool Furthermore, we revealed the target relationship between genes and miRNA using miRTarBase database and target prediction software, including miRanda and TargetScan. In addition, we visualized interaction networks and signalling pathways for these filtered miRNA and target genes. Finally, we compiled all the above data and information to generate a database designated DHDD This is the first comprehensive collection of human disease-related miRNA and their targeting genes conserved in a D. melanogaster database. The DHDD provides a resource for easily searching human disease-related miRNA and their disease-related target genes as well as their orthologs in D. melanogaster, and conveniently identifying the regulatory relationships among them in the form of a visual network.
Collapse
Affiliation(s)
- Guanyun Wei
- Laboratory for Comparative Genomics and Bioinformatics & Jiangsu Key Laboratory for Biodiversity and Biotechnology, College of Life Science, Nanjing Normal University, Nanjing 210046, Jiangsu, China.
- School of Life Sciences, School of Ocean Nantong University, Nantong 226019, Jiangsu, China.
| | - Lianjie Sun
- Laboratory for Comparative Genomics and Bioinformatics & Jiangsu Key Laboratory for Biodiversity and Biotechnology, College of Life Science, Nanjing Normal University, Nanjing 210046, Jiangsu, China.
| | - Shijie Qin
- Laboratory for Comparative Genomics and Bioinformatics & Jiangsu Key Laboratory for Biodiversity and Biotechnology, College of Life Science, Nanjing Normal University, Nanjing 210046, Jiangsu, China.
| | - Ruimin Li
- Laboratory for Comparative Genomics and Bioinformatics & Jiangsu Key Laboratory for Biodiversity and Biotechnology, College of Life Science, Nanjing Normal University, Nanjing 210046, Jiangsu, China.
| | - Liming Chen
- The Key Laboratory of Developmental Genes and Human Disease, College of Life Science, Nanjing Normal University, Nanjing 210046, Jiangsu, China.
| | - Ping Jin
- Laboratory for Comparative Genomics and Bioinformatics & Jiangsu Key Laboratory for Biodiversity and Biotechnology, College of Life Science, Nanjing Normal University, Nanjing 210046, Jiangsu, China.
| | - Fei Ma
- Laboratory for Comparative Genomics and Bioinformatics & Jiangsu Key Laboratory for Biodiversity and Biotechnology, College of Life Science, Nanjing Normal University, Nanjing 210046, Jiangsu, China.
| |
Collapse
|
4
|
Correia CN, Nalpas NC, McLoughlin KE, Browne JA, Gordon SV, MacHugh DE, Shaughnessy RG. Circulating microRNAs as Potential Biomarkers of Infectious Disease. Front Immunol 2017; 8:118. [PMID: 28261201 PMCID: PMC5311051 DOI: 10.3389/fimmu.2017.00118] [Citation(s) in RCA: 140] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2016] [Accepted: 01/25/2017] [Indexed: 12/12/2022] Open
Abstract
microRNAs (miRNAs) are a class of small non-coding endogenous RNA molecules that regulate a wide range of biological processes by post-transcriptionally regulating gene expression. Thousands of these molecules have been discovered to date, and multiple miRNAs have been shown to coordinately fine-tune cellular processes key to organismal development, homeostasis, neurobiology, immunobiology, and control of infection. The fundamental regulatory role of miRNAs in a variety of biological processes suggests that differential expression of these transcripts may be exploited as a novel source of molecular biomarkers for many different disease pathologies or abnormalities. This has been emphasized by the recent discovery of remarkably stable miRNAs in mammalian biofluids, which may originate from intracellular processes elsewhere in the body. The potential of circulating miRNAs as biomarkers of disease has mainly been demonstrated for various types of cancer. More recently, however, attention has focused on the use of circulating miRNAs as diagnostic/prognostic biomarkers of infectious disease; for example, human tuberculosis caused by infection with Mycobacterium tuberculosis, sepsis caused by multiple infectious agents, and viral hepatitis. Here, we review these developments and discuss prospects and challenges for translating circulating miRNA into novel diagnostics for infectious disease.
Collapse
Affiliation(s)
- Carolina N Correia
- Animal Genomics Laboratory, UCD School of Agriculture and Food Science, University College Dublin , Dublin , Ireland
| | - Nicolas C Nalpas
- Animal Genomics Laboratory, UCD School of Agriculture and Food Science, University College Dublin , Dublin , Ireland
| | - Kirsten E McLoughlin
- Animal Genomics Laboratory, UCD School of Agriculture and Food Science, University College Dublin , Dublin , Ireland
| | - John A Browne
- Animal Genomics Laboratory, UCD School of Agriculture and Food Science, University College Dublin , Dublin , Ireland
| | - Stephen V Gordon
- UCD School of Veterinary Medicine, University College Dublin, Dublin, Ireland; University College Dublin, UCD Conway Institute of Biomolecular and Biomedical Research, Dublin, Ireland
| | - David E MacHugh
- Animal Genomics Laboratory, UCD School of Agriculture and Food Science, University College Dublin, Dublin, Ireland; University College Dublin, UCD Conway Institute of Biomolecular and Biomedical Research, Dublin, Ireland
| | - Ronan G Shaughnessy
- UCD School of Veterinary Medicine, University College Dublin , Dublin , Ireland
| |
Collapse
|
5
|
Obtaining Human Ischemic Stroke Gene Expression Biomarkers from Animal Models: A Cross-species Validation Study. Sci Rep 2016; 6:29693. [PMID: 27407070 PMCID: PMC4942769 DOI: 10.1038/srep29693] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2016] [Accepted: 06/21/2016] [Indexed: 02/06/2023] Open
Abstract
Recent studies have revealed the systematic altering of gene expression in human peripheral blood during the early stages of ischemic stroke, which suggests a new potential approach for the rapid diagnosis or prediction of stroke onset. Nevertheless, due to the difficulties of collecting human samples during proper disease stages, related studies are rather restricted. Many studies have instead been performed on manipulated animal models for investigating the regulation patterns of biomarkers during different stroke stages. An important inquiry is how well the findings of animal models can be replicated in human cases. Here, a method is proposed based on PageRank scores of miRNA-mRNA interaction network to select ischemic stroke biomarkers derived from rat brain samples, and biomarkers are validated with two human peripheral blood gene expression datasets. Hierarchical clustering results revealed that the achieved biomarkers clearly separate the blood gene expression of stroke patients and healthy people. Literature searches and functional analyses further validated the biological significance of these biomarkers. Compared to the traditional methods, such as differential expression, the proposed approach is more stable and accurate in detecting cross-species biomarkers with biological relevance, thereby suggesting an efficient approach of re-using gene biomarkers obtained from animal-model studies for human diseases.
Collapse
|